Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    articles or descriptions

    oai_token-act-pair · gemini-2.0-flash

    summary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Datuak
    -0.52
    Enllaces
    -0.52
    AutoresizingMask
    -0.51
    jsii
    -0.44
     hasattr
    -0.43
    ordine
    -0.41
    vela
    -0.41
    幽
    -0.41
    спеди
    -0.41
    یل
    -0.41
    POSITIVE LOGITS
     overview
    1.14
     summary
    0.99
    overview
    0.90
     OVERVIEW
    0.88
     Überblick
    0.87
     synopsis
    0.84
     glimpse
    0.81
    OVERVIEW
    0.81
     Overview
    0.80
     insight
    0.80
    Act Density 1.630%

    No Known Activations